agentdb
It provides a unified architecture for agentic memory and reasoning, reducing the infrastructure complexity required to implement long-term episodic memory a…
Agent memory and vector database for AI agents: single-file HNSW search, episodic memory, causal graph, reinforcement learning and MCP tools.
- Store and retrieve long-term memories for AI agents in a single file
- Build causal graphs to track relationships between different pieces of agent data
- Provide AI agents with episodic memory to remember past user interactions
It provides a unified architecture for agentic memory and reasoning, reducing the infrastructure complexity required to implement long-term episodic memory and causal relationship tracking in autonomous workflows.
AI engineers building autonomous agents that require persistent memory and structured causal reasoning capabilities.
https://www.npmjs.com/package/agentdb
By ruvnet
How to Get It
npx agentdb
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me store and retrieve long-term memories for AI agents in a single file
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Agent-db-scan – See what a Postgres login can do — Hacker News · 3 pts
- Agent DB — Hacker News · 2 pts
- Generate product insights by giving your AI agent DB access and app source code — Hacker News · 1 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 97 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 97 GitHub stars; contributors unknown; last commit 0d ago; license MIT.